Locomotion is a basic act that humans and animals use in everyday life to move in the environment. There has been an ongoing effort for at least a century to understand the mechanisms that the brain uses to control locomotion, including starting and stopping. Studying those mechanisms at the level of single neurons, and finding […]

Learning from relational data is crucial for modeling the processes found in many application domains ranging from computational biology to social networks. In this project, we propose to work on developing new modeling techniques that combine the advantages of the approaches found in two fields of study: Machine Learning (through graph neural networks and transformer […]

Ce projet consiste à extraire la nature des accès informatiques des employés d’une organisation et les consolider afin de permettre au gestionnaire de l’employer ou à un auditeur d’avoir une vue d’ensemble des accès informatiques de ses employés. Les employés qui arrivent ou quittent l’organisation, ou changent d’emploi dans la même organisation exigent une révision […]

Predictive modeling of financial data, especially trading activity or asset prices, is a very challenging task. There are a number of novel approaches to feature engineering, data preparation and model architectures that aim to mitigate some of the problems that arise from non-stationarity and other issues typically found in financial time series data. This project […]

Liver failure is rapidly becoming a health epidemic in North America, mostly due to large increases in fatty liver disease. The liver normally clears ammonia from the bloodstream, however, when the liver fails ammonia builds up to dangerous levels and causes cognitive impairment which can progress to coma and death. Neuractas Therapeutics has developed a […]

Human perception has developed the ability to decompose scenes into fine grained elements. This lays the foundation for strong generalization to new situations where the base concepts can be recomposed to interpret objects never seen before. While it has been shown that, in the general case, proper decomposition is not possible, new paradigms provide provable […]

This research is carried out on the topic of natural language processing and specifically on word representation on Question Answering tasks. The state of the art in Question Answer task is Google’s Bidirectional Encoder Representations from Transformers (BERT) language model. Koïos Intelligence is interested in fine-tuning this model for their closed domain artificial intelligence (AI) […]

Développer un modèle prédictif en traitement automatique des langues requière la création d’un corpus annoté : un texte et des annotations que l’on tentera de reproduire automatiquement. Il s’agit d’une activité à la fois complexe (les annotations sont souvent du ressort d’un expert) et coûteuse (annotations méticuleuses à produire en grande quantité). Le projet vise […]

Développer un modèle prédictif en traitement automatique des langues requière la création d’un corpus annoté : un texte et des annotations que l’on tentera de reproduire automatiquement. Il s’agit d’une activité à la fois complexe (les annotations sont souvent du ressort d’un expert) et coûteuse (annotations méticuleuses à produire en grande quantité). Le projet vise […]

Cardiovascular clinical trials try to demonstrate the benefit of a medication on populations where the number of participants with the targeted disease is very low. The low efficacy of treatment is partially due to the diversity of diseases and of the population. To improve the efficacy of treatment, it is necessary to improve the recruitment […]

The analysis of large, complex data helps scientists from different fields (e.g. physics, chemistry, biology) to provide new insights on their research. The field of neuroscience is no different. Larger and more complex studies which create huge amount of data are more and more common. Thus, the development of tools capable of processing large datasets […]

Ce projet de recherche est intimement lie à l’optimisation et au contrôle qualité d’une technologie verte associée au recyclage du polystyrène (PS). Durant ce procédé, le PS contaminé provenant du consommateur ou simplement de rejets industriels est mis au contact d’un solvant qui a pour but de le solubiliser, puis d’un autre pour le précipiter. […]